CheeLinks       Search       All Topics       The World             Next       Previous       Expand Subtopics

Supertopics:
Possible Artificial Intelligence Dangers 2025, part two
Generative Artificial Intelligence, part two
Lying Miscellany

top AI models will lie, cheat and steal to reach goals      web

webhttps://www.axios.com/2025/06/20/ai-models-deceive-steal-blackmail-anthropic
authorIna Fried
publicationAxios
date2025-06-20

Documents:
AI systems blackmail execs who may shut them down
webMichael NuñezVentureBeat2025-06-20
agentic misalignment (LLMs as insider threats)
webAnthropic2025-06-20

To visit the web page, click the title or the word "web" or the URL.